Opening book details…
Can I read An Ultra-Low-Power Image Signal Processor for Hierarchical Image Recognition With Deep Neural Networks on EtoBox?
An Ultra-Low-Power Image Signal Processor for Hierarchical Image Recognition With Deep Neural Networks by Hyochan An; Sam Schiferl; Siddharth Venkatesan; Tim Wesley; Qirui Zhang; Jingcheng Wang; Kyojin D. Choo; Shiyu Liu; Bowen Liu; Ziyun Li; Luyao Gong; Hengfei Zhong; David Blaauw; Ronald Dreslinski; Hun Seok Kim; Dennis Sylvester is a Engineering article available to read on EtoBox.
What is An Ultra-Low-Power Image Signal Processor for Hierarchical Image Recognition With Deep Neural Networks about?
We propose an ultra-low-power (ULP) image signal processor (ISP) that performs on-the-fly in-processing frame compression/decompression and hierarchical event recognition to exploit the temporal and spatial sparsity in an image sequence. This approach reduces energy consumption spent processing and transmitting unimportant image data to achieve a 16× imaging system energy gain in an intruder detection scenario. The ISP was fabricated in 40-nm CMOS and consumes only 170 μW at 5 frames/s for neural network-based intruder detection and 192× compressed image recording. Index Terms-Deep neural network (DNN), energy-efficient processor, event recognition, image compression, image signal processor (ISP). ## I. INTRODUCTION T HE Internet of Things (IoT) is ubiquitous in many applications, such as smart homes, smart cities, and smart agriculture [1]. Battery-operated millimeter (mm)-scale IoT devices are desired solutions for embedding sensors in physical spaces due to their wireless operation and tiny form factor [2]. Imaging is a highly desirable sensing modality in these devices as it offers key contextual information about a system's environment. However, imaging requires a large amount
Who reads An Ultra-Low-Power Image Signal Processor for Hierarchical Image Recognition With Deep Neural Networks?
It is typically read by researchers, students, and practitioners in Engineering.
- Author
- Hyochan An; Sam Schiferl; Siddharth Venkatesan; Tim Wesley; Qirui Zhang; Jingcheng Wang; Kyojin D. Choo; Shiyu Liu; Bowen Liu; Ziyun Li; Luyao Gong; Hengfei Zhong; David Blaauw; Ronald Dreslinski; Hun Seok Kim; Dennis Sylvester
- Publisher
- Institute of Electrical and Electronics Engineers (IEEE)
- Published
- 2021
- Language
- EN
- Field
- Engineering (Physical Sciences)